
%%javascript
// JS snippet to save the notebook as html file to display the plotly graphs 
require.config({
  paths: {
    d3: 'https://cdnjs.cloudflare.com/ajax/libs/d3/5.9.2/d3',
    jquery: 'https://code.jquery.com/jquery-3.4.1.min',
    plotly: 'https://cdn.plot.ly/plotly-latest.min'
  },

  shim: {
    plotly: {
      deps: ['d3', 'jquery'],
      exports: 'plotly'
    }
  }
});


import pandas as pd
import numpy as np
import plotly.graph_objects as go
import plotly.express as px
import plotly.subplots as sp
import plotly.figure_factory as ff
from itertools import cycle
import re


pd.set_option('display.max_columns', 100)
pd.set_option('display.max_rows', 100)
pd.set_option('display.max_colwidth', None)


df = pd.read_csv("data/titles.csv")


df.head(1)


df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 5806 entries, 0 to 5805
Data columns (total 15 columns):
 #   Column                Non-Null Count  Dtype  
---  ------                --------------  -----  
 0   id                    5806 non-null   object 
 1   title                 5805 non-null   object 
 2   type                  5806 non-null   object 
 3   description           5788 non-null   object 
 4   release_year          5806 non-null   int64  
 5   age_certification     3196 non-null   object 
 6   runtime               5806 non-null   int64  
 7   genres                5806 non-null   object 
 8   production_countries  5806 non-null   object 
 9   seasons               2047 non-null   float64
 10  imdb_id               5362 non-null   object 
 11  imdb_score            5283 non-null   float64
 12  imdb_votes            5267 non-null   float64
 13  tmdb_popularity       5712 non-null   float64
 14  tmdb_score            5488 non-null   float64
dtypes: float64(5), int64(2), object(8)
memory usage: 680.5+ KB


df.describe().T


palette = cycle(px.colors.sequential.thermal)

fig = sp.make_subplots(
    rows=3, cols=3,
    subplot_titles=[
        "Yearwise Release Count",
        "Runtime",
        "IMDB Votes",
        "IMDB Rating",
        "TMDB Popularity",
        "TMDB Score",
        "Seasons",
        "Age Certification",
        "Movie Or Show"],
    specs=[[{"type": "histogram"}, {"type": "histogram"}, {"type": "histogram"}],
           [{"type": "histogram"}, {"type": "histogram"}, {"type": "histogram"}],
           [{"type": "histogram"}, {"type": "pie"}, {"type": "pie"}]]
)

release_year = go.Histogram(
    x=df.release_year,
    name="Release Year",
    marker_color=next(palette),
    legendgroup="Release Year",
    legendgrouptitle_text="Release Year",
)

runtime = go.Histogram(
    x=df.runtime,
    nbinsx=int(df.__len__()/50),
    name="Runtime",
    marker_color=next(palette),
    legendgroup="Runtime",
    legendgrouptitle_text="Runtime",
)

imdb_votes = go.Histogram(
    x=df.imdb_votes,
    nbinsx=int(df.__len__()/50),
    name="IMDB Votes",
    marker_color=next(palette),
    legendgroup="IMDB Votes",
    legendgrouptitle_text="IMDB Votes",
)

imdb_score = go.Histogram(
    x=df.imdb_score,
    nbinsx=10,
    name="IMDB Score",
    marker_color=next(palette),
    legendgroup="IMDB Score",
    legendgrouptitle_text="IMDB Score",
)

tmdb_popularity = go.Histogram(
    x=df.tmdb_popularity,
    name="TMDB Popularity",
    nbinsx=int(df.__len__()/50),
    marker_color=next(palette),
    legendgroup="TMDB Popularity",
    legendgrouptitle_text="TMDB Popularity",
)

tmdb_score = go.Histogram(
    x=df.tmdb_score,
    name="TMDB Score",
    nbinsx=10,
    marker_color=next(palette),
    legendgroup="TMDB Score",
    legendgrouptitle_text="TMDB Score",
)

seasons = go.Histogram(
    x=df.seasons,
    name="Seasons",
    marker_color=next(palette),
    legendgroup="Seasons",
    legendgrouptitle_text="Seasons",
)

age_certification_counts = df.age_certification.value_counts()
age_certification_counts["Not Available"] = df.age_certification.isna().sum()
age_certification_dict = age_certification_counts.to_dict()

age_certification = go.Pie(
    labels=list(age_certification_dict.keys()),
    values=list(age_certification_dict.values()),
    name="Age Certification",
    hoverinfo="label+value+percent",
    marker_colors=[next(palette) for i in range(len(age_certification_dict))],
    legendgroup="Age Certification",
    legendgrouptitle_text="Age Certification",
)

type_counts = df.type.value_counts().to_dict()

type_ = go.Pie(
    labels=list(type_counts.keys()),
    values=list(type_counts.values()),
    name="Type",
    hoverinfo="label+value+percent",
    marker_colors=[next(palette) for i in range(len(type_counts))],
    legendgroup="Type",
    legendgrouptitle_text="Type",
)

fig.add_trace(release_year, row=1, col=1)
fig.update_xaxes(title_text="Release Year", row=1, col=1)
fig.update_yaxes(title_text="Count", row=1, col=1)

fig.add_trace(runtime, row=1, col=2)
fig.update_xaxes(title_text="#Runtime", row=1, col=2)
fig.update_yaxes(title_text="Count", row=1, col=2)

fig.add_trace(imdb_votes, row=1, col=3)
fig.update_xaxes(title_text="No. of IMDB Votes", row=1, col=3)
fig.update_yaxes(title_text="Count", row=1, col=3)

fig.add_trace(imdb_score, row=2, col=1)
fig.update_xaxes(title_text="#IMDB Score", row=2, col=1)
fig.update_yaxes(title_text="Count", row=2, col=1)

fig.add_trace(tmdb_popularity, row=2, col=2)
fig.update_xaxes(title_text="#TMDB Popularity", row=2, col=2)
fig.update_yaxes(title_text="Count", row=2, col=2)

fig.add_trace(tmdb_score, row=2, col=3)
fig.update_xaxes(title_text="#TMDB Score", row=2, col=3)
fig.update_yaxes(title_text="Count", row=2, col=3)  

fig.add_trace(seasons, row=3, col=1)
fig.update_xaxes(title_text="No. of Seasons", row=3, col=1)
fig.update_yaxes(title_text="Count", row=3, col=1)

fig.add_trace(age_certification, row=3, col=2)

fig.add_trace(type_, row=3, col=3)

fig.update_annotations(font_size=23)

fig.update_layout(
    template="plotly",
    height=1400,
)

fig.update(
    layout_title_text="Distribution of Characteristics of Movies and Series",
    layout_title_font_size=30,
    layout_title_x=0.5,
    layout_paper_bgcolor='rgb(229, 237, 247)',
    layout_plot_bgcolor='rgb(229, 237, 247)',
)

fig.show(renderer='notebook')


palette = cycle(px.colors.qualitative.Dark2_r)

fig = sp.make_subplots(
    rows=2, cols=3,
    subplot_titles=["Runtime",
                    "Seasons",
                    "IMDB Score",
                    "IMDB Votes",
                    "TMDB Popularity",
                    "TMDB Score",],
    specs=[[{"type": "box"}, {"type": "box"}, {"type": "box"}],
           [{"type": "box"}, {"type": "box"}, {"type": "box"}]],
)

runtime_box = go.Box(
    y=df.runtime,
    name="Runtime",
    marker_color=next(palette),
)

seasons_box = go.Box(
    y=df.seasons,
    name="Seasons",
    marker_color=next(palette),
)

imdb_score_box = go.Box(
    y=df.imdb_score,
    name="IMDB Score",
    marker_color=next(palette),
)

imdb_votes_box = go.Box(
    y=df.imdb_votes,
    name="IMDB Votes",
    marker_color=next(palette),
)

tmdb_popularity_box = go.Box(
    y=df.tmdb_popularity,
    name="TMDB Popularity",
    marker_color=next(palette),
)

tmdb_score_box = go.Box(
    y=df.tmdb_score,
    name="TMDB Score",
    marker_color=next(palette),
)

fig.add_trace(runtime_box, row=1, col=1)
fig.update_xaxes(title_text="Runtime", row=1, col=1)

fig.add_trace(seasons_box, row=1, col=2)
fig.update_xaxes(title_text="No. of Seasons", row=1, col=2)

fig.add_trace(imdb_score_box, row=1, col=3)
fig.update_xaxes(title_text="IMDB Score", row=1, col=3)

fig.add_trace(imdb_votes_box, row=2, col=1)
fig.update_xaxes(title_text="No. of IMDB Votes", row=2, col=1)

fig.add_trace(tmdb_popularity_box, row=2, col=2)
fig.update_xaxes(title_text="TMDB Popularity", row=2, col=2)

fig.add_trace(tmdb_score_box, row=2, col=3)
fig.update_xaxes(title_text="TMDB Score", row=2, col=3)


fig.update_layout(template="plotly", height=1080,)
fig.update_annotations(font_size=23)

fig.update(
    layout_title_text="Box Plots of Characteristics of Movies and Series",
    layout_title_font_size=30,
    layout_title_x=0.5,
    layout_paper_bgcolor='rgb(229, 237, 247)',
    layout_plot_bgcolor='rgb(229, 237, 247)',
)

fig.show(renderer='notebook')


df["genres"] = df["genres"].apply(lambda x: re.findall("\w+", x))

genres = list(df["genres"].values)
genres = list(set([item for sublist in genres for item in sublist]))

for i, genre in enumerate(genres):
    df[genre] = df.genres.apply(lambda x: 1 if genre in x else 0).astype(int)

print("Number of Genres: ", len(genres))
print("Genres:", genres)

Number of Genres:  19
Genres: ['crime', 'european', 'action', 'animation', 'reality', 'thriller', 'war', 'history', 'romance', 'fantasy', 'scifi', 'drama', 'western', 'comedy', 'music', 'family', 'sport', 'horror', 'documentation']


genre_movie_dict = {}

for genre in genres:
    genre_movie_dict[genre] = df.query("type == 'MOVIE'")[genre].sum()

genre_movie_dict = dict(sorted(genre_movie_dict.items(), key=lambda x: x[0]))

genre_series_dict = {}

for genre in genres:
    genre_series_dict[genre] = df.query("type == 'SHOW'")[genre].sum()

genre_series_dict = dict(sorted(genre_series_dict.items(), key=lambda x: x[0]))

fig = sp.make_subplots(
    rows=2,
    cols=1,
    subplot_titles=["Movies", "Series"],
)

genre_movie_count = go.Bar(
    x=list(genre_movie_dict.keys()),
    y=list(genre_movie_dict.values()),
    marker=dict(color=list(genre_movie_dict.values()),
                colorscale=px.colors.qualitative.Dark2),
    name="Movies",
)

genre_series_count = go.Bar(
    x=list(genre_series_dict.keys()),
    y=list(genre_series_dict.values()),
    marker=dict(color=list(genre_series_dict.values()),
                colorscale=px.colors.qualitative.Dark2),
    name="Series",
)

fig.add_trace(genre_movie_count, row=1, col=1)
fig.update_xaxes(title_text="Genres", row=1, col=1)
fig.update_yaxes(title_text="Count", row=1, col=1)

fig.add_trace(genre_series_count, row=2, col=1)
fig.update_xaxes(title_text="Genres", row=2, col=1)
fig.update_yaxes(title_text="Count", row=2, col=1)

fig.update(
    layout_title_text="Genre Distribution based on No. of Movies and Shows",
    layout_title_font_size=30,
    layout_title_x=0.5,
    layout_template="plotly",
    layout_showlegend=False,
    layout_height=800,
    layout_paper_bgcolor='rgb(229, 237, 247)',
    layout_plot_bgcolor='rgb(229, 237, 247)',
)

fig.update_annotations(font_size=18)

fig.show(renderer='notebook')


genre_movies_popularity_dict = {}

for i, genre in enumerate(genres):
    genre_movies_popularity_dict[genre] = df.query("type == 'MOVIE'").groupby(genre)["imdb_votes"].sum().sort_index().__getitem__(1)

genre_movies_popularity_dict = dict(sorted(genre_movies_popularity_dict.items(), key=lambda x: x[0]))

genre_series_popularity_dict = {}

for i, genre in enumerate(genres):
    genre_series_popularity_dict[genre] = df.query("type == 'SHOW'").groupby(genre)["imdb_votes"].sum().sort_index().__getitem__(1)

genre_series_popularity_dict = dict(sorted(genre_series_popularity_dict.items(), key=lambda x: x[0]))

fig = sp.make_subplots(
    rows=2, 
    cols=1,
    subplot_titles=["Movies", "Series"],
)

genre_movies_pop = go.Bar(
    x=list(genre_movies_popularity_dict.keys()),
    y=list(genre_movies_popularity_dict.values()),
    marker=dict(color=list(genre_movies_popularity_dict.values()),
                colorscale=px.colors.qualitative.Dark2),
    hoverinfo="x+y",
)

genre_series_pop = go.Bar(
    x=list(genre_series_popularity_dict.keys()),
    y=list(genre_series_popularity_dict.values()),
    marker=dict(color=list(genre_series_popularity_dict.values()),
                colorscale=px.colors.qualitative.Dark2),
    hoverinfo="x+y",
)

fig.add_trace(genre_movies_pop, row=1, col=1)
fig.update_xaxes(title_text="Genre", row=1, col=1)
fig.update_yaxes(title_text="IMDB Votes", row=1, col=1)
fig.update

fig.add_trace(genre_series_pop, row=2, col=1)
fig.update_xaxes(title_text="Genre", row=2, col=1)
fig.update_yaxes(title_text="IMDB Votes", row=2, col=1)

fig.update(
    layout_title_text="Genre Distribution based on IMDB Votes",
    layout_title_font_size=30,
    layout_title_x=0.5,
    layout_template="plotly",
    layout_showlegend=False,
    layout_height=800,
    layout_paper_bgcolor='rgb(229, 237, 247)',
    layout_plot_bgcolor='rgb(229, 237, 247)',
)

fig.update_annotations(font_size=18)

fig.show(renderer='notebook')


palette = cycle(px.colors.qualitative.Dark2)

fig = go.Figure()

for i, genre in enumerate(sorted(genres)):
    temp = df[df[genre] == 1]
    
    fig.add_trace(
        go.Box(
            y=temp['imdb_score'],
            name=genre,
            marker_color=next(palette),
            marker_size=5,
            line_width=1,
            hovertemplate="<b>%{y:.2f}</b>"+f"<br>{genre}<br>Count-{len(temp)}<extra></extra>",
        )
    )

fig.update_layout(
    title="IMDB Score Box Distribution by Genre",
    title_font_size=30,
    title_x=0.5,
    yaxis_title="IMDB Score",
    xaxis_title="Genre",
    template="plotly",
    margin=dict(
        l=40,
        r=30,
        b=80,
        t=100,
    ),
    showlegend=False,
    paper_bgcolor='rgb(229, 237, 247)',
    plot_bgcolor='rgb(229, 237, 247)',
)

fig.show(renderer='notebook')


fig = ff.create_distplot(
    [df[(df[genre] == 1) & (df['imdb_score'].notna())]['imdb_score'] for genre in sorted(genres)],
    sorted(genres),
    show_hist=False,
    show_rug=False,
)

fig.update_layout(
    title="IMDB Score Distribution by Genre",
    title_font_size=30,
    title_x=0.5,
    xaxis_title="IMDB Score",
    template="plotly",
    paper_bgcolor='rgb(229, 237, 247)',
    plot_bgcolor='rgb(229, 237, 247)',
    legend_title="Genre",
)

fig.show(renderer='notebook')


df["production_countries"] = df["production_countries"].apply(lambda x: re.findall("\w+", x))

df["production_countries"] = df["production_countries"].apply(lambda x: ["LB"] if str(x).__contains__("Lebanon") else x)

df["production_countries"] = df["production_countries"].apply(lambda x: [] if str(x).__contains__("XX") else x)

production_countries = list(df["production_countries"].values)
production_countries = list(set([item for sublist in production_countries for item in sublist]))

df["main_production_country_alpha_2"] = df.production_countries.apply(lambda x: x[0] if x else None)

country_alpha = pd.read_json("data/countries.json")[["name", "alpha_2", "alpha_3"]]
country_alpha = dict(zip(country_alpha.alpha_2, country_alpha.alpha_3))

df["main_production_country_alpha_3"] = df.main_production_country_alpha_2.apply(lambda x: country_alpha[x] if x else None)

fig = go.Figure()

map_plot = go.Choropleth(
    locations=df.main_production_country_alpha_3.value_counts().index, 
    z=df.main_production_country_alpha_3.value_counts().values,
    colorscale="Reds",
    autocolorscale=False,
    colorbar_title="No. of Movies",
)

fig.update_layout(
    title_text="Production Countries",
    title_font_size=30,
    height=680,
    title_x=0.5,
    geo=dict(
        showframe=False,
        showcoastlines=False,
        projection_type='equirectangular'
    ),
)

fig.add_trace(map_plot)


distrib = df['imdb_score'].map(lambda x: f"{int(np.nan_to_num(x)*10//10)}-{int((np.nan_to_num(x)*10//10)+1)}")
df.insert(12, 'imdb_score_range', distrib)

score_range_dict = {}

for i, genre in enumerate(sorted(genres)):
    score_range_dict[genre] = df.groupby(genre)['imdb_score_range'].value_counts().__getitem__(1).to_dict()


fig = sp.make_subplots(
    rows=4, 
    cols=5,
    subplot_titles=sorted(genres),
    specs=[[{'type': 'table'}]*5]*4,
    horizontal_spacing=0.01,
    vertical_spacing=0.05,
)

for i, (key, value) in enumerate(score_range_dict.items()):
    fig.append_trace(
        go.Table(
            header=dict(
                values=["IMDB Score Range", "Count"],
                align="center",
            ),
            cells=dict(
                values=[list(value.keys()), list(value.values())],
                align="center",  
            )
        ),
        row=i%4+1,
        col=i%5+1,   
    )

fig.update_layout(
    title_text="IMDB Score Distribution by Genre",
    title_font_size=30,
    title_x=0.5,
    height=1000,
    autosize=True,
)
fig.show(renderer='notebook')


df.query("type == 'MOVIE'")[['release_year',
                             'title',
                             'type',
                             'runtime',
                             'imdb_score',
                             'imdb_votes',
                             'genres']]\
    .sort_values(by=["imdb_votes", "imdb_score"],
                 ascending=False)\
    .head(5)\
    .reset_index(drop=True)


df.query("type == 'SHOW'")[['release_year',
                            'title',
                            'type',
                            'runtime',
                            'imdb_score',
                            'imdb_votes',
                            'genres',
                            ]]\
    .sort_values(by=["imdb_votes", "imdb_score"],
                 ascending=False)\
    .head(5)\
    .reset_index(drop=True)


df.query("type == 'SHOW' and main_production_country_alpha_3 == 'USA' and age_certification == 'TV-PG'")\
    .sort_values(by=["imdb_votes", "imdb_score"], ascending=False)\
    .reset_index(drop=True)\
    .head(1)\
    [["id", "title", "release_year", "genres", "seasons", "runtime", "imdb_score", "imdb_votes"]]


best_by_genre = pd.DataFrame(columns=df.columns.tolist() + ["selected_genre"])

for i, genre in enumerate(sorted(genres)):
    best_genre_data = df.query(f"{genre} == 1").sort_values(by=["imdb_votes", "imdb_score"], ascending=False).reset_index().head(1)
    best_genre_data["selected_genre"] = genre
    
    best_by_genre = pd.concat([best_by_genre, best_genre_data], ignore_index=True).reset_index(drop=True)

best_by_genre[['release_year', 'title', 'selected_genre', 'imdb_score']]


gb = df.query("type == 'SHOW'")\
        .sort_values(by=["release_year", "imdb_score"], ascending=[True, False])\
        .groupby("release_year")

gb.first()[["title", "imdb_score"]]


df[(df['drama'] == 1) & 
   (df['thriller'] == 1) & 
   (df['main_production_country_alpha_3'] == 'IND')
   ].sort_values(by=["imdb_score"], ascending=False)\
    .reset_index(drop=True)\
    .head(5)\
    .loc[:, ["title", "release_year", "imdb_score"]]


df[(df['action'] == 1) &
   (df['comedy'] == 1) &
   (df['main_production_country_alpha_3'] == 'GBR')
   ]\
   .sort_values(by=["imdb_score"], ascending=False)\
   .reset_index(drop=True)\
   .head(5)\
   .loc[:, ["title", "release_year", "imdb_score"]]


total_produced_countries = df.groupby("main_production_country_alpha_3")['title'].count().to_dict()
country_alpha = pd.read_json("data/countries.json")[["name", "alpha_2", "alpha_3"]]
country_alpha3_name = country_alpha.set_index("alpha_3")["name"].to_dict()

count = 0

for (key, value) in total_produced_countries.items():
    if value < 5:
        count += 1
        if count % 4 == 0:
            print(f"[{count}] {country_alpha3_name[key]} ({key})", end="\n")
        else:
            print(f"[{count}] {country_alpha3_name[key]} ({key})", end="\t")

[1] Afghanistan (AFG)	[2] Angola (AGO)	[3] Bangladesh (BGD)	[4] Belarus (BLR)
[5] Switzerland (CHE)	[6] Cameroon (CMR)	[7] Congo (the Democratic Republic of the) (COD)	[8] Cuba (CUB)
[9] Algeria (DZA)	[10] Finland (FIN)	[11] Georgia (GEO)	[12] Ghana (GHA)
[13] Greenland (GRL)	[14] Guatemala (GTM)	[15] Croatia (HRV)	[16] Hungary (HUN)
[17] British Indian Ocean Territory (IOT)	[18] Iraq (IRQ)	[19] Jordan (JOR)	[20] Kenya (KEN)
[21] Kyrgyzstan (KGZ)	[22] Cambodia (KHM)	[23] Lithuania (LTU)	[24] Luxembourg (LUX)
[25] Morocco (MAR)	[26] Mozambique (MOZ)	[27] Mauritius (MUS)	[28] Malawi (MWI)
[29] Namibia (NAM)	[30] Pakistan (PAK)	[31] Puerto Rico (PRI)	[32] Portugal (PRT)
[33] Paraguay (PRY)	[34] Senegal (SEN)	[35] Serbia (SRB)	[36] Slovakia (SVK)
[37] Syria (SYR)	[38] Tanzania, the United Republic of (TZA)	[39] Ukraine (UKR)	[40] Uruguay (URY)
[41] Venezuela (Bolivarian Republic of) (VEN)	[42] Viet Nam (VNM)	[43] Zimbabwe (ZWE)


longest_runtime = pd.DataFrame(columns=df.columns.tolist() + ["selected_genre"])

for i, genre in enumerate(sorted(genres)):
    temp = df[df[genre] == 1].sort_values(by=['runtime'], ascending=False).reset_index(drop=True)
    first = temp.groupby(genre).first()
    first["selected_genre"] = genre
    longest_runtime = pd.concat([longest_runtime, first], ignore_index=True).reset_index(drop=True)

longest_runtime[['title', 'release_year', 'runtime', 'selected_genre']]


df.sort_values(by=['seasons'], ascending=False)\
    .reset_index(drop=True)\
    .head(5)\
    .loc[:, ["title", "release_year", "seasons", "genres"]]


!jupyter nbconvert --to html analysis.ipynb

[NbConvertApp] Converting notebook analysis.ipynb to html
c:\users\keshav\anaconda3\envs\pytorch_env\lib\site-packages\nbconvert\filters\widgetsdatatypefilter.py:69: UserWarning: Your element with mimetype(s) dict_keys(['application/vnd.plotly.v1+json']) is not able to be represented.
  warn("Your element with mimetype(s) {mimetypes}"
[NbConvertApp] Writing 27130767 bytes to analysis.html

	count	mean	std	min	25%	50%	75%	max
release_year	5806.0	2016.013434	7.324883	1945.000000	2015.00000	2018.000	2020.00000	2022.000
runtime	5806.0	77.643989	39.474160	0.000000	44.00000	84.000	105.00000	251.000
seasons	2047.0	2.165608	2.636207	1.000000	1.00000	1.000	2.00000	42.000
imdb_score	5283.0	6.533447	1.160932	1.500000	5.80000	6.600	7.40000	9.600
imdb_votes	5267.0	23407.194988	87134.315849	5.000000	521.00000	2279.000	10144.00000	2268288.000
tmdb_popularity	5712.0	22.525660	68.849177	0.009442	3.15525	7.478	17.77575	1823.374
tmdb_score	5488.0	6.818039	1.171560	0.500000	6.10000	6.900	7.50000	10.000

	release_year	title	type	runtime	imdb_score	imdb_votes	genres
0	2010	Inception	MOVIE	148	8.8	2268288.0	[scifi, music, thriller, action]
1	1994	Forrest Gump	MOVIE	142	8.8	1994599.0	[drama, romance, comedy]
2	2012	Django Unchained	MOVIE	165	8.4	1472668.0	[western, drama]
3	1998	Saving Private Ryan	MOVIE	169	8.6	1346020.0	[drama, war]
4	1976	Taxi Driver	MOVIE	113	8.3	795222.0	[crime, drama]

	release_year	title	type	runtime	imdb_score	imdb_votes	genres
0	2008	Breaking Bad	SHOW	48	9.5	1727694.0	[drama, thriller, crime]
1	2016	Stranger Things	SHOW	52	8.7	989090.0	[scifi, drama, fantasy, horror, thriller]
2	2010	The Walking Dead	SHOW	46	8.2	945125.0	[action, drama, scifi, thriller, horror]
3	2011	Black Mirror	SHOW	59	8.8	515577.0	[scifi, thriller, drama, european]
4	2013	House of Cards	SHOW	52	8.7	494092.0	[drama]

	release_year	title	selected_genre	imdb_score
0	2010	Inception	action	8.8
1	2010	How to Train Your Dragon	animation	8.1
2	1994	Forrest Gump	comedy	8.8
3	2008	Breaking Bad	crime	9.5
4	2002	Road to Perdition	documentation	7.7
5	1994	Forrest Gump	drama	8.8
6	2006	Casino Royale	european	8.0
7	2010	How to Train Your Dragon	family	8.1
8	2016	Stranger Things	fantasy	8.7
9	2017	Dunkirk	history	7.8
10	2016	Stranger Things	horror	8.7
11	2010	Inception	music	8.8
12	2017	GLOW	reality	8.0
13	1994	Forrest Gump	romance	8.8
14	2010	Inception	scifi	8.8
15	2013	Rush	sport	8.1
16	2010	Inception	thriller	8.8
17	1998	Saving Private Ryan	war	8.6
18	2012	Django Unchained	western	8.4

	title	imdb_score
release_year
1945	Five Came Back: The Reference Films	NaN
1969	Monty Python's Flying Circus	8.8
1972	Monty Python's Fliegender Zirkus	8.1
1981	Danger Mouse	7.4
1982	Knight Rider	6.9
1983	Wheel of Fortune	6.7
1984	Thomas & Friends	6.5
1987	Fireman Sam	6.1
1988	High Risk	3.8
1989	Seinfeld	8.9
1991	My First Errand	NaN
1992	Barney & Friends	3.8
1993	Star Trek: Deep Space Nine	8.1
1994	The Magic School Bus	7.8
1995	Neon Genesis Evangelion	8.5
1996	Moesha	5.7
1997	Stargate SG-1	8.4
1998	Cowboy Bebop	8.9
1999	One Piece	8.8
2000	Okupas	9.0
2001	Trailer Park Boys	8.6
2002	Still Game	8.9
2003	Chappelle's Show	8.8
2004	The Staircase	7.8
2005	Khawatir	9.6
2006	DEATH NOTE	9.0
2007	Heartland	8.4
2008	Breaking Bad	9.5
2009	Midnight Diner	8.6
2010	Downton Abbey	8.7
2011	Hunter x Hunter	9.0
2012	Call the Midwife	8.5
2013	Attack on Titan	9.0
2014	Raja, Rasoi Aur Anya Kahaniyaan	9.0
2015	Reply 1988	9.2
2016	Leah Remini: Scientology and the Aftermath	9.0
2017	Crazy Delicious	8.9
2018	#ABtalks	9.6
2019	Our Planet	9.3
2020	The Last Dance	9.1
2021	Arcane	9.1
2022	Who Rules The World	9.2

Netflix Analysis¶

Import Libraries¶

Loading the Dataset¶

Quick Look into the dataset¶

Basic Information¶

Distribution of All the Features¶

Box Plot of All the Features¶

Feature Generation¶

Genre Distribution¶

Based on Count¶

Based on IMDB Votes¶

IMDB Score Box Plot by Genre¶

IMDB Score Dist (KDE) Plot by Genre¶

Production Countries¶

IMDB Score Category¶

Questionnaire¶

1. TOP 5 Movies with High IMDB Votes and Score¶

2. TOP 5 Series with High IMDB Votes and Score¶

3. Best PG TV Show in terms of both IMDB Votes and Score produced in US¶

4. Best Movie or TV Show for every Genre in terms of both IMDB Votes and Score¶

5. List All the US Best TV Show yearwise with the highest IMDB Score¶

6. Top 5 Thriller and Drama Indian Movies to watch¶

7. Top 5 Action and Comedy British Series to watch¶

8. List the countries which have produced less than 5 movies or shows¶

9. The longest movie ever made in terms of duration for every genre¶

10. Longest Series ever made in terms of seasons¶

Save the notebook as html file to display the plotly graphs¶

	title	release_year	imdb_score
0	Sacred Games	2018	8.6
1	Super Deluxe	2019	8.4
2	Single Slipper Size - 7	2019	8.4
3	Article 15	2019	8.2
4	Andhadhun	2018	8.2

	title	release_year	imdb_score
0	Octonauts	2010	7.6
1	Danger Mouse	2015	7.2
2	Sugar Rush	2019	6.7
3	Thomas & Friends	1984	6.5
4	David Brent: Life on the Road	2016	6.3

	title	release_year	runtime	selected_genre
0	Jodhaa Akbar	2008	213	action
1	Mobile Suit Gundam III: Encounters in Space	1982	144	animation
2	The School of Mischief	1973	251	comedy
3	Bonnie & Clyde	2013	240	crime
4	A Lion in the House	2006	225	documentation
5	Bonnie & Clyde	2013	240	drama
6	Bonnie & Clyde	2013	240	european
7	4K Fireplace	2015	181	family
8	Hum Saath Saath Hain	1999	177	fantasy
9	Jodhaa Akbar	2008	213	history
10	Apocalypse Now Redux	2001	196	horror
11	No Direction Home: Bob Dylan	2005	208	music
12	4K Fireplace	2015	181	reality
13	Lagaan: Once Upon a Time in India	2001	224	romance
14	Blade Runner 2049	2017	164	scifi
15	Lagaan: Once Upon a Time in India	2001	224	sport
16	The Irishman	2019	209	thriller
17	Jodhaa Akbar	2008	213	war
18	The Hateful Eight: Extended Version	2019	199	western

	title	release_year	seasons	genres
0	Survivor	2000	42.0	[reality]
1	Wheel of Fortune	1983	39.0	[family]
2	The Challenge	1998	37.0	[reality, comedy, drama, scifi]
3	Power Rangers	1993	29.0	[scifi, action, fantasy, family]
4	Pokémon	1997	24.0	[scifi, action, comedy, fantasy, animation, family]